• Nuclear Engineering and Technology
• /
• v.45 no.6
• /
• pp.759-766
• /
• 2013

As passive safety features for nuclear power plants receive increasing attention, various studies have been conducted to develop safety systems for 3rd-generation (GEN-III) nuclear power plants that are driven by passive systems. The Passive Auxiliary Feedwater System (PAFS) is one of several passive safety systems being designed for the Advanced Power Reactor Plus (APR+), and extensive studies are being conducted to complete its design and to verify its feasibility. Because the PAFS removes decay heat from the reactor core under transient and accident conditions, it is necessary to evaluate the heat removal capability of the PAFS under hypothetical accident conditions. The heat removal capability of the PAFS is strongly dependent on the heat transfer at the condensate tube in Passive Condensation Heat Exchanger (PCHX). To evaluate the model of heat transfer coefficient for condensation, the Multi-dimensional Analysis of Reactor Safety (MARS) code is used to simulate the experimental results from PAFS Condensing Heat Removal Assessment Loop (PASCAL). The Shah model, a default model for condensation heat transfer coefficient in the MARS code, under-predicts the experimental data from the PASCAL. To improve the calculation result, The Thome model and the new version of the Shah model are implemented and compared with the experimental data.

• Journal of Software Engineering Society
• /
• v.29 no.1
• /
• pp.13-21
• /
• 2020

As CNN model is applied to various domains such as image classification and object detection, the performance of CNN model which is used to safety critical system like autonomous vehicles should be reliable. To evaluate that CNN model can sustain the performance in various environments, we developed an image data augmentation apparatus which generates images that is changed background. If an image which contains object is entered into the apparatus, it extracts an object image from the entered image and generate s composed images by synthesizing the object image with collected background images. A s a method to evaluate a CNN model, the apparatus generate s new test images from original test images, and we evaluate the CNN model by the new test image. As a case study, we generated new test images from Pascal VOC2007 and evaluated a YOLOv3 model with the new images. As a result, it was detected that mAP of new test images is almost 0.11 lower than mAP of the original test images.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.5
• /
• pp.195-204
• /
• 2018

In this paper, we propose both a new loss function and an online hard example mining scheme for improving the performance of single-stage object detectors which use deep convolutional neural networks. The proposed loss function and the online hard example mining scheme can not only overcome the problem of imbalance between the number of annotated objects and the number of background examples, but also improve the localization accuracy of each object. Therefore, the loss function and the mining scheme can provide intrinsically fast single-stage detectors with detection performance higher than or similar to that of two-stage detectors. In experiments conducted with the PASCAL VOC 2007 benchmark dataset, we show that the proposed loss function and the online hard example mining scheme can improve the performance of single-stage object detectors.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2000.11a
• /
• pp.1.2-24
• /
• 2000

The field of neural networks has been a recent surge in activity as a result of progress in developments of efficient training algorithms. For this reason, and coupled with the widespread availability of powerful personal computer hardware for running simulations of networks, there is increasing focus on the potential benefits this field can offer. The neural network may be viewed as an advanced pattern recognition technique and can be applied in many areas such as financial time series forecasting, medical diagnostic expert system and etc.. The intention of this study is to build and implement one simple artificial neural networks hereinafter called ANN. For this purpose, some literature survey was undertaken to understand the structures and algorithms of ANN theoretically. Based on the review of theories about ANN, the system adopted 3-layer back propagation algorithms as its learning algorithm to simulate one case of medical diagnostic model. The adopted ANN algorithm was performed in PC by using turbo PASCAL and many input parameters such as the numbers of layers, the numbers of nodes, the number of cycles for learning, learning rate and momentum term. The system output more or less successful results which nearly agree with goals we assumed. However, the system has some limitations such as the simplicity of the programming structure and the range of parameters it can dealing with. But, this study is useful for understanding general algorithms and applications of ANN system and can be expanded for further refinement for more complex ANN algorithms.

• Journal of the Korea Convergence Society
• /
• v.8 no.7
• /
• pp.15-21
• /
• 2017

Recently, users' interest in IoT related products is increasing as the 4th industrial revolution has become social. The types and functions of sensors used in IoT devices are becoming increasingly diverse, and mutual authentication technology of IoT devices is required. In this paper, we propose an efficient double signature authentication scheme using Pascal's triangle theory so that different types of IoT devices can operate smoothly with each other. The proposed scheme divides the authentication path between IoT devices into two (main path and auxiliary path) to guarantee authentication and integrity of the IoT device. In addition, the proposed scheme is suitable for IoT devices that require a small capacity because they generate keys so that additional encryption algorithms are unnecessary when authenticating IoT devices. As a result of the performance evaluation, the delay time of the IoT device is improved by 6.9% and the overhead is 11.1% lower than that of the existing technique. The throughput of IoT devices was improved by an average of 12.5% over the existing techniques.

• Journal of Convergence for Information Technology
• /
• v.11 no.9
• /
• pp.28-34
• /
• 2021

In the case of object detection using deep learning, both accuracy and real-time are required. However, it is difficult to use a deep learning model that processes a large amount of data in a limited resource environment. To solve this problem, this paper proposes an object detection model for small embedded devices. Unlike the general detection model, the model size was minimized by using a structure in which the pre-trained feature extractor was removed. The structure of the model was designed by repeatedly stacking lightweight convolution blocks. In addition, the number of region proposals is greatly reduced to reduce detection overhead. The proposed model was trained and evaluated using the public dataset PASCAL VOC. For quantitative evaluation of the model, detection performance was measured with average precision used in the detection field. And the detection speed was measured in a Raspberry Pi similar to an actual embedded device. Through the experiment, we achieved improved accuracy and faster reasoning speed compared to the existing detection method.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.4
• /
• pp.2181-2184
• /
• 2013

Prostate cancer is the most common malignancy in men in the United States. Surgery or radiation are sometimes unsatisfactory treatments because of the complications such as incontinence or erectile dysfunction. Selenium was found to be effective to preven prostate cancer in the Nutritional Prevention of Cancer Trial (NPC), which motivated two other clinical trials: the Selenium and Vitamin E Cancer Prevention Trial (SELECT) and a Phase III trial of selenium to prevent prostate cancer in men with high-grade prostatic intraepithelial neoplasia. However, these two trials failed to confirm the results of the NPC trial and indicated that the selenium may not be preventive of prostate cancer. In this article we review the three clinical trials and discuss some different points which might be potential factors underlying variation in results obtained.

• ETRI Journal
• /
• v.27 no.1
• /
• pp.13-21
• /
• 2005

Many multicast applications, such as video-on-demand and video conferencing, desire quality of service (QoS) support from an underlying network. The differentiated services (DiffServ) approach will bring benefits for theses applications. However, difficulties arise while integrating native IP multicasting with DiffServ, such as multicast group states in the core routers and a heterogeneous QoS requirement within the same multicast group. In addition, a missing per-flow reservation in DiffServ and a dynamic join/leave in the group introduce heavier and uncontrollable traffic in a network. In this paper, we propose a distributed and stateless admission control in the edge routers. We also use a mobile agents-based approach for dynamic resource availability checking. In this approach, mobile agents act in a parallel and distributed fashion and cooperate with each other in order to construct the multicast tree satisfying the QoS requirements.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.282-285
• /
• 2004

Every year, the last products from most important builders of high bandwidth digitizers are tested in our laboratory which is specialized in the design and the characterization of fast links used in large laser facility. The purpose of this article is to describe the series of tests conducted during the characterization of such digitizers. More particularly, it takes an interest in the metrology of instruments with more than 5 GHz of bandwidth. It presents the different methods used and the kind of conclusion that we can give after such study. Such metrology campaign which usually takes one month of work, allows us to observe the smallest details and characteristics that usually builders don't give in their tables specifications. After the campaign, a copy of our technical report is written and sends to the builder. This report can be used by the technical team to ameliorate the points we noted.